{"id":"https://openalex.org/W2032632402","doi":"https://doi.org/10.1145/1344671.1344718","title":"Efficient FPGA implementation of qr decomposition using a systolic array architecture","display_name":"Efficient FPGA implementation of qr decomposition using a systolic array architecture","publication_year":2008,"publication_date":"2008-02-24","ids":{"openalex":"https://openalex.org/W2032632402","doi":"https://doi.org/10.1145/1344671.1344718","mag":"2032632402"},"language":"en","primary_location":{"id":"doi:10.1145/1344671.1344718","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1344671.1344718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international ACM/SIGDA symposium on Field programmable gate arrays","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100346006","display_name":"Xiaojun Wang","orcid":"https://orcid.org/0000-0002-6802-2623"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojun Wang","raw_affiliation_strings":["Airvana, Chelmsford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airvana, Chelmsford, MA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083047329","display_name":"Miriam Leeser","orcid":"https://orcid.org/0000-0002-5624-056X"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miriam Leeser","raw_affiliation_strings":["Northeastern University, Boston, MA","Northeastern University, Boston (MA)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Northeastern University, Boston (MA)#TAB#","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"260","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.823488712310791},{"id":"https://openalex.org/keywords/cordic","display_name":"CORDIC","score":0.780885636806488},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.759617269039154},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7435144186019897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314891815185547},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.7224778532981873},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.693497896194458},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.5758106708526611},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5418551564216614},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.489091694355011},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.4680855870246887},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4063493311405182},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3276926875114441},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32551196217536926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.214045912027359},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.12136462330818176},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.10668450593948364}],"concepts":[{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.823488712310791},{"id":"https://openalex.org/C58870171","wikidata":"https://www.wikidata.org/wiki/Q116076","display_name":"CORDIC","level":3,"score":0.780885636806488},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.759617269039154},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7435144186019897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314891815185547},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.7224778532981873},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.693497896194458},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.5758106708526611},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5418551564216614},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.489091694355011},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.4680855870246887},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4063493311405182},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3276926875114441},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32551196217536926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.214045912027359},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.12136462330818176},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.10668450593948364},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1344671.1344718","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1344671.1344718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international ACM/SIGDA symposium on Field programmable gate arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2004703634","https://openalex.org/W3150370983","https://openalex.org/W2239119680","https://openalex.org/W3022016791","https://openalex.org/W1638830944","https://openalex.org/W1986095997","https://openalex.org/W2981274774","https://openalex.org/W2301399139","https://openalex.org/W2532436914","https://openalex.org/W1986431723"],"abstract_inverted_index":{"QR":[0,15,158],"decomposition":[1,16],"is":[2,53,160,181],"used":[3],"in":[4],"many":[5],"signal":[6],"processing":[7],"applications.":[8],"We":[9,64,122],"have":[10],"implemented":[11],"a":[12,18,29,119,164,184],"systolic":[13,33],"array":[14,34],"on":[17],"Xilinx":[19],"Virtex5":[20],"FPGA":[21,151],"using":[22,55],"the":[23,45,56,98],"Givens":[24],"rotation":[25],"algorithm.":[26],"It":[27],"uses":[28,76,89],"truly":[30],"two":[31],"dimensional":[32],"architecture":[35],"so":[36],"latency":[37],"scales":[38],"well":[39],"for":[40,170,183],"large":[41],"matrices.":[42,128],"To":[43],"accommodate":[44],"dynamic":[46],"range":[47],"of":[48,166],"input":[49,130],"data,":[50],"floating-point":[51,68,78,174],"arithmetic":[52],"chosen,":[54],"Northeastern":[57],"University":[58],"Variable":[59],"Precision":[60],"Floating-Point":[61],"(VFloat)":[62],"library.":[63],"support":[65,123],"any":[66,140],"general":[67],"format":[69],"including":[70],"IEEE":[71,171],"single":[72,172],"precision.":[73],"Our":[74],"design":[75,106],"straightforward":[77],"divide":[79],"and":[80,109,126],"square":[81],"root":[82],"implementations,":[83],"compared":[84],"to":[85,111,116,138,148],"prior":[86],"work":[87],"which":[88],"special":[90],"operations":[91],"or":[92,97,153],"formats":[93],"such":[94],"as":[95],"CORDIC":[96],"logarithmic":[99],"number":[100],"system":[101],"(LNS).":[102],"This":[103],"makes":[104],"our":[105],"more":[107],"standard":[108],"portable":[110],"different":[112],"systems,":[113],"thus":[114],"easier":[115],"fit":[117],"into":[118],"larger":[120,150],"design.":[121],"square,":[124],"tall":[125],"short":[127],"The":[129,157],"matrix":[131,188],"size":[132],"can":[133,144],"be":[134,145],"configured":[135],"at":[136],"compile-time":[137],"virtually":[139],"size.":[141],"Therefore,":[142],"it":[143],"easily":[146],"scaled":[147],"future":[149],"devices,":[152],"over":[154,167],"multiple":[155],"FPGAs.":[156],"module":[159],"fully":[161],"pipelined":[162],"with":[163,189],"throughput":[165,178],"130":[168],"MHz":[169],"precision":[173],"format.":[175],"35":[176],"GFlops":[177],"peak":[179],"performance":[180],"achieved":[182],"12":[185,187],"by":[186],"this":[190],"implementation":[191]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}